Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    say numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     注意
    -0.07
    -G
    -0.06
    -0.06
    注意
    -0.06
     चर
    -0.06
     یا
    -0.06
     IMapper
    -0.06
    Night
    -0.06
     --------------------
    -0.06
    \Persistence
    -0.06
    POSITIVE LOGITS
     closeModal
    0.07
     adress
    0.07
    ong
    0.06
    sit
    0.06
    veedor
    0.06
    .Light
    0.06
    recursive
    0.06
     Hopefully
    0.06
    opacity
    0.06
    lessly
    0.06
    Act Density 0.001%

    No Known Activations